Hostname: page-component-848d4c4894-75dct Total loading time: 0 Render date: 2024-06-01T06:56:19.326Z Has data issue: false hasContentIssue false
  • English
  • Français

Design of an optimized gait planning generator for a quadruped robot using the decision tree and random forest workspace model

Published online by Cambridge University Press:  18 October 2023

Yifan Wu Open the ORCID record for Yifan Wu [Opens in a new window] ,
Sheng Guo ,
Zheqi Yu Open the ORCID record for Zheqi Yu [Opens in a new window] ,
Peiyi Wang ,
Lianzheng Niu  and
Majun Song
Yifan Wu
Affiliation:
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, 100044, China
Sheng Guo*
Affiliation:
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, 100044, China
Zheqi Yu
Affiliation:
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, 100044, China
Peiyi Wang
Affiliation:
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, 100044, China
Lianzheng Niu
Affiliation:
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, 100044, China
Majun Song
Affiliation:
Hangzhou Innovation Institute, Beihang University, Hangzhou, Zhejiang, 310051, China
*
Corresponding author: Sheng Guo; Email: shguo@bjtu.edu.cn
Get access Rights & Permissions [Opens in a new window]

Abstract

Real-time gait trajectory planning is challenging for legged robots walking on unknown terrain. In this paper, to realize a more efficient and faster motion control of a quadrupedal robot, we propose an optimized gait planning generator (GPG) based on the decision tree (DT) and random forest (RF) model of the robot leg workspace. First, the framework of this embedded GPG and some of the modules associated with it are illustrated. Aiming at the leg workspace model described by DT and RF used in GPG, this paper introduces in detail how to collect the original data needed for training the model and puts forward an Interpolation Labeling with Dilation and Erosion (ILDE) data processing algorithm. After the DT and RF models are trained, we preliminarily evaluate their performance. We then present how these models can be used to predict the location relation between a spatial point and the leg workspace based on its distributional features. The DT model takes only 0.00011 s to process a sample, while the RF model can give the prediction probability. As a complement, the PID inverse kinematic model used in GPG is also mentioned. Finally, the optimized GPG is tested during a real-time single-leg trajectory planning experiment and an unknown terrain recognition simulation of a virtual quadrupedal robot. According to the test results, the GPG shows a remarkable rapidity for processing large-scale data in the gait trajectory planning tasks, and the results can prove it has an application value for quadruped robot control.

Keywords

quadruped robotrobot workspacelocomotion controlgait planningdecision treerandom forest
Type
Research Article
Information
Robotica , Volume 41 , Issue 12 , December 2023 , pp. 3746 - 3771
Copyright
© The Author(s), 2023. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Nguyen, Q., Powell, M. J., Katz, B., Carlo, J. D. and Kim, S., “Optimized Jumping on the MIT Cheetah 3 Robot,” In: 2019 International Conference on Robotics and Automation (ICRA) (2019) pp. 7448–7454. doi: 10.1109/ICRA.2019.8794449.CrossRefGoogle Scholar
Katz, B., Carlo, J. D. and Kim, S., “Mini Cheetah: A Platform for Pushing the Limits of Dynamic Quadruped Control,” In: 2019 International Conference on Robotics and Automation (ICRA) (2019) pp. 6295–6301. doi: 10.1109/ICRA.2019.8793865.CrossRefGoogle Scholar
Arm, P., Zenkl, R., Barton, P., Beglinger, L., Dietsche, A., Ferrazzini, L., Hampp, E., Hinder, J., Huber, C., Schaufelberger, D., Schmitt, F., Sun, B., Stolz, B., Kolvenbach, H. and Hutter, M., “SpaceBok: A Dynamic Legged Robot for Space Exploration,” In: 2019 International Conference on Robotics and Automation (ICRA) (2019) pp. 6288–6294. doi: 10.1109/ICRA.2019.8794136.CrossRefGoogle Scholar
Hutter, M., Gehring, C., Lauber, A., Gunther, F., Bellicoso, C. D., Tsounis, V., Fankhauser, P., Diethelm, R., Bachmann, S., Bloesch, M., Kolvenbach, H., Bjelonic, M., Isler, L. and Meyer, K., “ANYmal - toward legged robots for harsh environments,” Adv. Robot. 31(17), 918–931 (2017). doi: 10.1080/01691864.2017.1378591.CrossRefGoogle Scholar
Buchanan, R., Wellhausen, L., Bjelonic, M., Bandyopadhyay, T., Kottege, N. and Hutter, M., “Perceptive whole-body planning for multilegged robots in confined spaces,” J. Field Robot. 38(1), 68–84 (2020). doi: 10.1002/rob.21974.CrossRefGoogle Scholar
Fukuoka, Y., Kimura, H., Hada, Y. and Takase, K., “Adaptive Dynamic Walking of a Quadruped Robot ‘Tekken’ on Irregular Terrain Using a Neural System Model,” In: 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422) (2003) pp. 2037–2042. doi: 10.1109/ROBOT.2003.1241893.CrossRefGoogle Scholar
Kimura, H. and Fukuoka, Y., “Biologically Inspired Adaptive Dynamic Walking in Outdoor Environment Using a Self-Contained Quadruped Robot: ‘Tekken2,” In: 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566) (2004) pp. 986–991. doi: 10.1109/IROS.2004.1389481.CrossRefGoogle Scholar
Raibert, M. H. and Tello, E. R., “Legged robots that balance,” IEEE Expert 1(4), 89–89 (1986). doi: 10.1109/MEX.1986.4307016.CrossRefGoogle Scholar
Yang, J.-M., “Two-phase discontinuous gaits for quadruped walking machines with a failed leg,” Robot. Auton. Syst. 56(9), 728–737 (2008). doi: 10.1016/j.robot.2008.01.002.CrossRefGoogle Scholar
Omori, Y., Kojio, Y., Ishikawa, T., Kojima, K., Sugai, F., Kakiuchi, Y., Okada, K. and Inaba, M., “Autonomous Safe Locomotion System for Bipedal Robot Applying Vision and Sole Reaction Force to Footstep Planning,” In: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2019) pp. 4891–4898. doi: 10.1109/IROS40897.2019.8968196.CrossRefGoogle Scholar
Hyun, D. J., Seok, S., Lee, J. and Kim, S., “High speed trot-running: Implementation of a hierarchical controller using proprioceptive impedance control on the MIT Cheetah,” Int. J. Robot. Res. 33(11), 1417–1445 (2014). doi: 10.1177/0278364914532150.CrossRefGoogle Scholar
Zeng, X., Zhang, S., Zhang, H., Li, X., Zhou, H. and Fu, Y., “Leg trajectory planning for quadruped robots with high-speed trot gait,” Appl. Sci. 9(7), 1508 (2019). doi: 10.3390/app9071508.CrossRefGoogle Scholar
Fankhauser, P., Bjelonic, M., Bellicoso, C. D., Miki, T. and Hutter, M., “Robust Rough-Terrain Locomotion with a Quadrupedal Robot,” In: 2018 IEEE International Conference on Robotics and Automation (ICRA) (2018) pp. 5761–5768. doi: 10.1109/ICRA.2018.8460731.CrossRefGoogle Scholar
Tieck, J. C. V., Rutschke, J., Kaiser, J., Schulze, M., Buettner, T., Reichard, D., Roennau, A. and Dillmann, R., “Combining Spiking Motor Primitives with a Behaviour-Based Architecture to Model Locomotion for Six-Legged Robots,” In: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2019) pp. 4161–4168. doi: 10.1109/IROS40897.2019.8968128.CrossRefGoogle Scholar
Chen, Z. and Gao, F., “Time-optimal trajectory planning method for six-legged robots under actuator constraints,” Proc. Inst. Mech. Eng. C. J. Mech. Eng. Sci. 233(14), 4990–5002 (2019). doi: 10.1177/0954406219833077.CrossRefGoogle Scholar
Kim, Y., Son, B. and Lee, D., “Learning multiple gaits of quadruped robot using hierarchical reinforcement learning,” arXiv e-prints (2021). doi: 10.48550/arXiv.2112.04741.Google Scholar
Shao, Y., Jin, Y., Liu, X., He, W., Wang, H. and Yang, W., “Learning free gait transition for quadruped robots via phase-guided controller,” IEEE Robot. Autom. Lett. 7(2), 1230–1237 (2022). doi: 10.1109/LRA.2021.3136645.CrossRefGoogle Scholar
Li, X., Gao, H., Li, J., Wang, Y. and Guo, Y., “Hierarchically planning static gait for quadruped robot walking on rough terrain,” J. Robot. 2019, 1–12 (2019). doi: 10.1155/2019/3153195.CrossRefGoogle Scholar
Takei, Y., Morishita, K., Tazawa, R., Katsuya, K. and Saito, K., “Non-programmed gait generation of quadruped robot using pulse-type hardware neuron models,” Artif. Life Robot. 26(1), 109–115 (2021). doi: 10.1007/s10015-020-00637-z.CrossRefGoogle Scholar
Gupta, K. C., “On the nature of robot workspace,” Int. J. Robot. Res. 5(2), 112–121 (1986). doi: 10.1177/027836498600500212.CrossRefGoogle Scholar
Kumar, A. and Waldron, K. J., “The workspaces of a mechanical manipulator,” J. Mech. Des. 103(3), 665–672 (1981). doi: 10.1115/1.3254968.Google Scholar
Ricard, R. and Gosselin, C. M., “On the determination of the workspace of complex planar robotic manipulators,” J. Mech. Des. 120(2), 269–278 (1998). doi: 10.1115/1.2826968.CrossRefGoogle Scholar
Snyman, J. A., du Plessis, L. J. and Duffy, J., “An optimization approach to the determination of the boundaries of manipulator workspaces,” J. Mech. Des. 122(4), 447–456 (2000). doi: 10.1115/1.1289388.CrossRefGoogle Scholar
Cao, Y., Qi, S., Lu, K., Zang, Y. and Yang, G., “An Integrated Method for Workspace Computation of Robot Manipulator,” In: 2009 International Joint Conference on Computational Sciences and Optimization (2009) pp. 309–312. doi: 10.1109/CSO.2009.161.CrossRefGoogle Scholar
Benbrahim, H. and Franklin, J. A., “Biped dynamic walking using reinforcement learning,” Robot. Auton. Syst. 22(3), 283–302 (1997). doi: 10.1016/S0921-8890(97)00043-2.CrossRefGoogle Scholar
Wang, S., Chaovalitwongse, W. and Babuska, R., “Machine learning algorithms in bipedal robot control,” IEEE Trans. Syst. Man Cybern. C Appl. Rev. 42(5), 728–743 (2012). doi: 10.1109/TSMCC.2012.2186565.CrossRefGoogle Scholar
Hwangbo, J., Lee, J., Dosovitskiy, A., Bellicoso, D., Tsounis, V., Koltun, V. and Hutter, M., “Learning agile and dynamic motor skills for legged robots,” Sci. Robot. 4(26), (2019). doi: 10.1126/scirobotics.aau5872.CrossRefGoogle ScholarPubMed
Pratt, J., Chew, C.-M., Torres, A., Dilworth, P. and Pratt, G., “Virtual model control: An intuitive approach for bipedal locomotion,” Int. J. Robot. Res. 20(2), 129–143 (2001). doi: 10.1177/02783640122067309.CrossRefGoogle Scholar
Song, Y., Zuo, J., Wu, J., Liu, Z. and Li, Z., “Robot Perceptual Classification Method Based on Mixed Features of Decision Tree and Random Forest,” In: 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE) (2021) pp. 919–922. doi: 10.1109/ICBAIE52039.2021.9389973.CrossRefGoogle Scholar
Zhang, M.-L. and Zhou, Z.-H., “ML-KNN: A lazy learning approach to multi-label learning,” Pattern Recogn. 40(7), 2038–2048 (2007). doi: 10.1016/j.patcog.2006.12.019.CrossRefGoogle Scholar
Chih-Wei, H. and Chih-Jen, L., “A comparison of methods for multiclass support vector machines,” IEEE Trans. Neural Netw. 13(2), 415–425 (2002). doi: 10.1109/72.991427.CrossRefGoogle Scholar
Liu, H., Song, X., Nanayakkara, T., Seneviratne, L. D. and Althoefer, K., “A Computationally Fast Algorithm for Local Contact Shape and Pose Classification Using a Tactile Array Sensor,” In: 2012 IEEE International Conference on Robotics and Automation (2012) pp. 1410–1415. doi: 10.1109/ICRA.2012.6224872.CrossRefGoogle Scholar
Ester, M., Kriegel, H.-P., Sander, J. and Xu, X., “A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise,” In: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (AAAI Press, Portland, OR, 1996) pp. 226–231.Google Scholar
Xu, X., Ester, M., Kriegel, H.-P. and Sander, J., “A Distribution-Based Clustering Algorithm for Mining in Large Spatial Databases,” In: Proceedings 14th International Conference on Data Engineering (1998) pp. 324–331. doi: 10.1109/ICDE.1998.655795.Google Scholar
Breiman, L., Classification and Regression Trees (Routledge, Boca Raton, 1984). doi: 10.1201/9781315139470.Google Scholar
Breiman, L., “Random forests,” Mach. Learn. 45(1), 5–32 (2001). doi: 10.1023/A:1010933404324.CrossRefGoogle Scholar
Luh, J., Walker, M. and Paul, R., “Resolved-acceleration control of mechanical manipulators,” IEEE Trans. Autom. Control 25(3), 468–474 (1980). doi: 10.1109/TAC.1980.1102367.CrossRefGoogle Scholar

Wu et al. supplementary material

Wu et al. supplementary material

Download Wu et al. supplementary material(Video)
Video 37.3 MB